The guides.
Step-by-step how-tos for recording, replaying, and gating AI agent workflows with Reelier. Every guide is runnable — real commands, verbatim output, no mockups — and links the terms it uses back to the glossary instead of redefining them.
How to snapshot-test a Claude Code workflow
The mental model is one line: the first run writes the snapshot, and every run after diffs against it.
How to record MCP tool calls with a wrap proxy
Some agents keep a transcript you can scan after the fact; some don't.
How to replay an agent workflow at 0 LLM tokens
A recorded agent workflow does not need a model to run again.
How to gate CI on agent drift
A drift gate turns "the agent quietly did something different" into a red build.
Replay an agent skill on every PR with the Reelier GitHub Action
This guide turns a recorded agent skill into a check that replays on every pull request and blocks the merge the moment the tool calls drift — with no model in the loop and 0 tokens per run.
Test your MCP server for regressions by replaying a golden run
The mental model is one line: put Reelier in front of your MCP server, record one healthy pass through the tools you ship, and freeze it as a golden run.
Run a deterministic cron agent by scheduling a recorded replay
A scheduled agent that re-reasons every wake-up pays the model bill on every single tick — the heartbeat tax.
Build an agent audit trail from Reelier run receipts
Every `reelier run` appends one line to `.reelier/runs/<skill>.jsonl`, written by the harness from observed results — not by the model, from memory.
Configure BYOK escalation levels: L0, L1, and L2
Reelier's escalation ladder is a spend ceiling you set per run.
Compile a skill from an existing session with reelier from-session
You already ran the workflow once — an agent pulled the data, checked the statuses, wrote the report, and you paid the tokens for it.
Diff two agent runs with reelier diff (exit 1 on drift)
`reelier diff <skill>` compares the last two runs of a compiled skill and turns any divergence into an exit code: it prints a per-step verdict, says `SAME` and exits 0 when the two runs are identical, and says `DRIFTED` and exits 1 the moment a step's outcome flips, a step is added or removed, or a step needed a different escalation level to pass.
Convert an LLM agent skill into a deterministic, assertion-checked skill
An LLM-executed skill is a `SKILL.md` full of prose: the model reads your instructions and decides the tool calls fresh on every run.